VQ-VAE
E755720
VQ-VAE is a neural network model that combines vector quantization with variational autoencoders to learn discrete latent representations for tasks like image and audio generation.
All labels observed (4)
| Label | Occurrences |
|---|---|
| VQ-VAE-2 | 3 |
| VQ-VAE canonical | 2 |
| Vector Quantized Variational Autoencoder | 2 |
| hierarchical VQ-VAE | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T8737777 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VQ-VAE Context triple: [Aaron van den Oord, developed, VQ-VAE]
-
A.
variational autoencoders
Variational autoencoders are a class of generative neural networks that learn probabilistic latent representations of data, enabling them to generate new, similar samples.
-
B.
Auto-Encoding Variational Bayes
Auto-Encoding Variational Bayes is the foundational 2013 paper by Kingma and Welling that introduced variational autoencoders, a generative model framework combining deep learning with variational Bayesian inference.
-
C.
WaveNet
WaveNet is a deep generative neural network architecture for raw audio that produces highly natural-sounding speech and other audio signals.
-
D.
Tacotron
Tacotron is a neural network-based text-to-speech system that generates natural-sounding speech by predicting mel-spectrograms from text, often used in conjunction with neural vocoders like Parallel WaveNet.
-
E.
Wav2Vec2
Wav2Vec2 is a self-supervised deep learning model for automatic speech recognition that learns powerful audio representations directly from raw waveforms.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: VQ-VAE Target entity description: VQ-VAE is a neural network model that combines vector quantization with variational autoencoders to learn discrete latent representations for tasks like image and audio generation.
-
A.
variational autoencoders
Variational autoencoders are a class of generative neural networks that learn probabilistic latent representations of data, enabling them to generate new, similar samples.
-
B.
Auto-Encoding Variational Bayes
Auto-Encoding Variational Bayes is the foundational 2013 paper by Kingma and Welling that introduced variational autoencoders, a generative model framework combining deep learning with variational Bayesian inference.
-
C.
WaveNet
WaveNet is a deep generative neural network architecture for raw audio that produces highly natural-sounding speech and other audio signals.
-
D.
Tacotron
Tacotron is a neural network-based text-to-speech system that generates natural-sounding speech by predicting mel-spectrograms from text, often used in conjunction with neural vocoders like Parallel WaveNet.
-
E.
Wav2Vec2
Wav2Vec2 is a self-supervised deep learning model for automatic speech recognition that learns powerful audio representations directly from raw waveforms.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf | neural network model ⓘ |
| addressesProblem |
learning discrete representations
ⓘ
posterior collapse in VAEs ⓘ |
| basedOn | variational autoencoder ⓘ |
| canBeExtendedTo |
VQ-VAE-2
ⓘ
linked to:
VQ-VAE
hierarchical VQ-VAE ⓘ
linked to:
VQ-VAE
|
| codebookSize | hyperparameter ⓘ |
| embeddingDimension | hyperparameter ⓘ |
| fullName |
Vector Quantized Variational Autoencoder
ⓘ
linked to:
VQ-VAE
|
| hasAdvantage |
avoids sampling from continuous latent distributions at training time
ⓘ
enables use of powerful autoregressive priors over codes ⓘ produces interpretable discrete codes ⓘ |
| hasComponent |
codebook
ⓘ
codebook loss term ⓘ commitment loss term ⓘ decoder ⓘ embedding vectors ⓘ encoder ⓘ reconstruction loss term ⓘ |
| hasLatentSpaceType | discrete latent space ⓘ |
| inputType |
audio waveforms
ⓘ
images ⓘ spectrograms ⓘ |
| inspired | subsequent discrete representation models ⓘ |
| introducedInPaper | Neural Discrete Representation Learning ⓘ |
| latentRepresentation | indices into a codebook of embeddings ⓘ |
| outputType |
reconstructed audio
ⓘ
reconstructed images ⓘ |
| primaryApplication |
audio generation
ⓘ
compression ⓘ image generation ⓘ representation learning ⓘ speech generation ⓘ |
| proposedBy |
Aaron van den Oord
ⓘ
Koray Kavukcuoglu ⓘ Oriol Vinyals ⓘ |
| publicationYear | 2017 ⓘ |
| publishedByOrganization | DeepMind ⓘ |
| usedWith |
PixelCNN prior
ⓘ
linked to:
PixelCNN
WaveNet prior ⓘ
linked to:
WaveNet
|
| usesOptimizationMethod |
Adam optimizer
ⓘ
stochastic gradient descent ⓘ |
| usesTechnique | vector quantization ⓘ |
| usesTrainingObjective |
codebook vector quantization
ⓘ
commitment loss regularization ⓘ reconstruction error minimization ⓘ |
| usesTrick | straight-through estimator ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: VQ-VAE Description of subject: VQ-VAE is a neural network model that combines vector quantization with variational autoencoders to learn discrete latent representations for tasks like image and audio generation.
Referenced by (8)
Full triples — surface form annotated when it differs from this entity's canonical label.
linked to: VQ-VAE
linked to: VQ-VAE
linked to: VQ-VAE
linked to: VQ-VAE
linked to: VQ-VAE